Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
ml-training-debugger
Diagnose and stabilize ML training runs, recover from failures, and deliver validated fixes.
majiayu000/claude-skill-registry 163
-
linq-optimization-patterns
Master LINQ and EF Core query optimization including N+1 prevention, eager loading, projections, and performance patterns. Use when: (1) fixing N+1 queries, (2) optimizing slow queries, (3) implementing efficient data access, (4) reducing database load.
majiayu000/claude-skill-registry 163
-
tracking-technical-debt
Use when you notice code problems while working on something else - links code markers to beads so issues don't get lost. Triggers on "I see a problem but can't fix it now."
majiayu000/claude-skill-registry 163
-
obsidian-note-formatting-skill
Create well-formatted Obsidian notes with proper frontmatter, templates, and organization. Use when users want to create notes for their Obsidian vault, document ideas or technical content, or need help structuring information in Obsidian-compatible markdown format.
majiayu000/claude-skill-registry 163
-
Framer Expert
Expert in Framer design and development - from interactive prototypes to production sites with Framer Motion, CMS integration, and the Framer MCP server
majiayu000/claude-skill-registry 163
-
anti-ai-validator
AI 탐지 가능 패턴을 감지하고 제거하는 독립 검증 스킬. 금지 표현, 반복 단어, 부자연스러운 구조를 탐지한다. 게시 전 콘텐츠를 검증하거나 AI 패턴을 자동 교정할 때 사용한다.
majiayu000/claude-skill-registry 163
-
pacing-analysis
Analyze narrative pacing and identify slow or rushed sections
majiayu000/claude-skill-registry 163
-
youtube-transcript-analyzer
Use when analyzing YouTube videos, extracting insights from tutorials, researching video content, or learning from talks and presentations
majiayu000/claude-skill-registry 163
-
nav-sop
Create Standard Operating Procedures after solving novel issues, establishing patterns, or documenting workflows. Use when user says "document this solution", "save this for next time", "create SOP".
majiayu000/claude-skill-registry 163
-
review-workflow
Complete quality assurance workflow orchestrating validation, comprehensive review, and functional testing. Sequential workflow from quality gating through multi-dimensional review to scenario testing. Use when conducting complete skill quality assurance, pre-deployment validation, or comprehensive quality checks combining multiple review approaches.
majiayu000/claude-skill-registry 163
-
commit.lint
Formats and lints code with ruff using a sub-agent. Use after tests pass to ensure code style compliance.
majiayu000/claude-skill-registry 163
-
infra-permission-manager
Manage IAM permissions - grant missing permissions when deployments fail, maintain IAM audit trail,
enforce profile separation, scope permissions to environment. Uses discover-deploy profile to grant
permissions, never grants to production without explicit approval.
majiayu000/claude-skill-registry 163
-
long-document-handler
Triggers when reading or writing documents exceeding 20,000 tokens (~80,000 characters or ~15,000 words). Use when encountering large files, lengthy documentation, big markdown documents, massive PRDs, architecture docs, or any content that risks context window overflow. Activates on phrases like "this document is long", "large file", "too many tokens", or when Claude detects document size approaching limits.
majiayu000/claude-skill-registry 163
-
docker-local-dev
Generate Docker Compose and Dockerfile configurations for local development through interactive Q&A. Supports PHP/Laravel, WordPress, Drupal, Joomla, Node.js, and Python stacks with Nginx, Supervisor/PM2, databases, Redis, and email testing. Always asks clarifying questions before generating configurations.
majiayu000/claude-skill-registry 163
-
proptest
Property-based testing for Rust using proptest. Use when writing tests that verify properties hold for arbitrary inputs, implementing custom strategies for generating test data, testing edge cases automatically, or when the user mentions "proptest", "property-based testing", "fuzz testing in Rust", "shrinking", or needs to generate arbitrary test data. Triggers include requests to test functions with random inputs, find edge cases, implement Arbitrary for custom types, or create data generators.
majiayu000/claude-skill-registry 163
-
web-developer-persistent-context
Advanced persistent context management system for web development work that never loses context between Claude Desktop sessions. Automatically tracks, saves, and restores all work context, session history, decisions, and progress across multiple sessions and projects.
majiayu000/claude-skill-registry 163
-
agentuity-cli-auth-org-unselect
Clear the default organization preference. Use for managing authentication credentials
majiayu000/claude-skill-registry 163
-
Localizing Variables
Declare variables in smallest possible scope, initialize close to first use, minimize span and live time
majiayu000/claude-skill-registry 163
-
ivangrynenko-cursorrules-drupal
Drupal development and security patterns from Ivan Grynenko's cursor rules. Covers OWASP Top 10, authentication, access control, injection prevention, cryptography, configuration, database standards, file permissions, and more.
majiayu000/claude-skill-registry 163
-
browser-screenshot
This skill should be used when users need to capture screenshots of web pages. It supports full-page screenshots, viewport-specific captures, responsive screenshots across multiple device sizes, and element-specific screenshots. Use this skill for visual testing, documentation, design reviews, or any task requiring automated browser screenshots.
majiayu000/claude-skill-registry 163
-
workflow-improvement
majiayu000/claude-skill-registry 163
-
Enterprise Orchestration
Advanced multi-agent coordination at scale for complex organizations
majiayu000/claude-skill-registry 163
-
azure-ai-agents-persistent-dotnet
Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools. Use for agent CRUD, conversation threads, streaming responses, function calling, file search, and code interpreter. Triggers: "PersistentAgentsClient", "persistent agents", "agent threads", "agent runs", "streaming agents", "function calling agents .NET".
majiayu000/claude-skill-registry 163
-
test-email
Send test email via Resend to verify template and delivery
majiayu000/claude-skill-registry 163